Team RAS in 10th ABAW Competition: Multimodal Valence and Arousal Estimation Approach

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ryumina, Elena, Markitantov, Maxim, Axyonov, Alexandr, Ryumin, Dmitry, Dolgushin, Mikhail, Dresvyanskiy, Denis, Karpov, Alexey
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912964944068608
author Ryumina, Elena
Markitantov, Maxim
Axyonov, Alexandr
Ryumin, Dmitry
Dolgushin, Mikhail
Dresvyanskiy, Denis
Karpov, Alexey
author_facet Ryumina, Elena
Markitantov, Maxim
Axyonov, Alexandr
Ryumin, Dmitry
Dolgushin, Mikhail
Dresvyanskiy, Denis
Karpov, Alexey
contents Continuous emotion recognition in terms of valence and arousal under in-the-wild (ITW) conditions remains a challenging problem due to large variations in appearance, head pose, illumination, occlusions, and subject-specific patterns of affective expression. We present a multimodal method for valence-arousal estimation ITW. Our method combines three complementary modalities: face, behavior, and audio. The face modality relies on GRADA-based frame-level embeddings and Transformer-based temporal regression. We use Qwen3-VL-4B-Instruct to extract behavior-relevant information from video segments, while Mamba is used to model temporal dynamics across segments. The audio modality relies on WavLM-Large with attention-statistics pooling and includes a cross-modal filtering stage to reduce the influence of unreliable or non-speech segments. To fuse modalities, we explore two fusion strategies: a Directed Cross-Modal Mixture-of-Experts Fusion Strategy that learns interactions between modalities with adaptive weighting, and a Reliability-Aware Audio-Visual Fusion Strategy that combines visual features at the frame-level while using audio as complementary context. The results are reported on the Aff-Wild2 dataset following the 10th Affective Behavior Analysis in-the-Wild (ABAW) challenge protocol. Experiments demonstrate that the proposed multimodal fusion strategy achieves a Concordance Correlation Coefficient (CCC) of 0.658 on the Aff-Wild2 development set.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13056
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Team RAS in 10th ABAW Competition: Multimodal Valence and Arousal Estimation Approach
Ryumina, Elena
Markitantov, Maxim
Axyonov, Alexandr
Ryumin, Dmitry
Dolgushin, Mikhail
Dresvyanskiy, Denis
Karpov, Alexey
Computer Vision and Pattern Recognition
Artificial Intelligence
Continuous emotion recognition in terms of valence and arousal under in-the-wild (ITW) conditions remains a challenging problem due to large variations in appearance, head pose, illumination, occlusions, and subject-specific patterns of affective expression. We present a multimodal method for valence-arousal estimation ITW. Our method combines three complementary modalities: face, behavior, and audio. The face modality relies on GRADA-based frame-level embeddings and Transformer-based temporal regression. We use Qwen3-VL-4B-Instruct to extract behavior-relevant information from video segments, while Mamba is used to model temporal dynamics across segments. The audio modality relies on WavLM-Large with attention-statistics pooling and includes a cross-modal filtering stage to reduce the influence of unreliable or non-speech segments. To fuse modalities, we explore two fusion strategies: a Directed Cross-Modal Mixture-of-Experts Fusion Strategy that learns interactions between modalities with adaptive weighting, and a Reliability-Aware Audio-Visual Fusion Strategy that combines visual features at the frame-level while using audio as complementary context. The results are reported on the Aff-Wild2 dataset following the 10th Affective Behavior Analysis in-the-Wild (ABAW) challenge protocol. Experiments demonstrate that the proposed multimodal fusion strategy achieves a Concordance Correlation Coefficient (CCC) of 0.658 on the Aff-Wild2 development set.
title Team RAS in 10th ABAW Competition: Multimodal Valence and Arousal Estimation Approach
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.13056